Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    formal statements and expressions of accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Attribution or quotations

    np_acts-logits-general · gemini-2.0-flash

    reporting what is said

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    testens
    -0.53
    ParallelGroup
    -0.51
     nhờ
    -0.47
     Bescheid
    -0.46
     informasi
    -0.45
    めで
    -0.45
    стоин
    -0.44
     hidupnya
    -0.44
    memberOf
    -0.44
     hans
    -0.44
    POSITIVE LOGITS
     pointing
    1.41
    Referring
    1.32
     saying
    1.29
     Referring
    1.29
     citing
    1.28
     stating
    1.28
     referring
    1.26
    Saying
    1.22
     stressing
    1.15
     noting
    1.12
    Act Density 0.155%

    No Known Activations